outman/dify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

improve the notion table extract (#7925)

Browse Source
This commit is contained in:
Jyong 2024-09-03 17:52:07 +08:00 committed by GitHub
parent 7fdd964379
commit 01581dd35f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
api/core/rag/extractor/notion_extractor.py
View File

@ -281,20 +281,25 @@ class NotionExtractor(BaseExtractor):
for table_header_cell_text in tabel_header_cell: for table_header_cell_text in tabel_header_cell:
text = table_header_cell_text["text"]["content"] text = table_header_cell_text["text"]["content"]
table_header_cell_texts.append(text) table_header_cell_texts.append(text)
# get table columns text and format else:
table_header_cell_texts.append('')
# Initialize Markdown table with headers
markdown_table = "| " + " | ".join(table_header_cell_texts) + " |\n"
markdown_table += "| " + " | ".join(['---'] * len(table_header_cell_texts)) + " |\n"
# Process data to format each row in Markdown table format
results = data["results"] results = data["results"]
for i in range(len(results) - 1): for i in range(len(results) - 1):
column_texts = [] column_texts = []
tabel_column_cells = data["results"][i + 1]['table_row']['cells'] table_column_cells = data["results"][i + 1]['table_row']['cells']
for j in range(len(tabel_column_cells)): for j in range(len(table_column_cells)):
if tabel_column_cells[j]: if table_column_cells[j]:
for table_column_cell_text in tabel_column_cells[j]: for table_column_cell_text in table_column_cells[j]:
column_text = table_column_cell_text["text"]["content"] column_text = table_column_cell_text["text"]["content"]
column_texts.append(f'{table_header_cell_texts[j]}:{column_text}') column_texts.append(column_text)
# Add row to Markdown table
cur_result_text = "\n".join(column_texts) markdown_table += "| " + " | ".join(column_texts) + " |\n"
result_lines_arr.append(cur_result_text) result_lines_arr.append(markdown_table)
if data["next_cursor"] is None: if data["next_cursor"] is None:
done = True done = True
break break